Space-Time Clustering for Object segmentation in video
A 3D Convolutional Approach to Spectral Object Segmentation in Space and Time
We formulate object segmentation in video as a graph partitioning problem in space and time, in which nodes are pixels and their relations form local neighborhoods.We claim that the strongest cluster in this pixel-level graphrepresents the salient object segmentation.We compute the main cluster using a novel and fast 3d filtering technique that finds the spectral clustering solution, namely the principal eigenvector of the graph s adjacency matrix, without building the matrix explicitly-which would be intractable.This allows us to avoid creating the matrix and have a fast parallel implementation on gpu.In experiments, we obtain consistent improvement, with the same set of hyper-parameters, over the top state of the art methods on davis-2016 dataset, both in unsupervised and semi-supervised tasks.We also achieve top results on the well-known segtrackv2 dataset.
